© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103170
    Prev
    Next
    INDEX
    Explanations

    viewing and managing data

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron spikes on programming‐style tokens—identifiers (often with underscores or CamelCase) and numeric literals—i.e. bits of code rather than ordinary words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    countDown
    -0.93
    chalten
    -0.91
     hemos
    -0.87
     engan
    -0.85
    farbe
    -0.85
    Noticia
    -0.85
    andır
    -0.84
    newGame
    -0.84
     Révolution
    -0.83
     AuthService
    -0.82
    POSITIVE LOGITS
     search
    1.88
     view
    1.85
     delete
    1.67
     viewing
    1.65
     show
    1.52
     display
    1.47
     see
    1.46
     list
    1.41
     edit
    1.41
     update
    1.39
    Activations Density 0.012%

    No Known Activations